Fancier string escape sequences and a bit of cleanup.

12 files changed, 21 insertions, 16 deletions

diff --git a/bp.1 b/bp.1
index 99c6afa..ee920b1 100644
--- a/bp.1
+++ b/bp.1
@@ -10,7 +10,7 @@ bp \- Bruce's Parsing Expression Grammar tool
 [\fI-e\fR|\fI--explain\fR]
 [\fI-j\fR|\fI--json\fR]
 [\fI-l\fR|\fI--list-files\fR]
-[\fI-i\fR|\fI--ignore-case\fR \fI<pattern>\fR]
+[\fI-i\fR|\fI--ignore-case\fR]
 [\fI-I\fR|\fI--inplace\fR]
 [\fI-C\fR|\fI--confirm\fR]
 [\fI-p\fR|\fI--pattern\fR \fI<pattern>\fR]
@@ -19,10 +19,12 @@ bp \- Bruce's Parsing Expression Grammar tool
 [\fI-g\fR|\fI--grammar\fR \fI<grammar file>\fR]
 [\fI-G\fR|\fI--git\fR]
 [\fI-c\fR|\fI--context\fR \fI<N>\fR]
-\fI<pattern\fR
+\fI<pattern>\fR
 [[--] \fI<input files...>\fR]
+
 .SH DESCRIPTION
 \fBbp\fR is a tool that matches parsing expression grammars using a custom syntax.
+
 .SH OPTIONS
 .B \-v\fR, \fB--verbose
 Print debugging information.
diff --git a/bp.c b/bp.c
index 7899ff0..b01c5b4 100644
--- a/bp.c
+++ b/bp.c
@@ -36,7 +36,7 @@ static const char *description = (
     BP_NAME" - a Parsing Expression Grammar command line tool");
 static const char *usage = (
     "Usage:\n"
-    "  "BP_NAME" [flags] <pattern> [<input files>...]\n\n"
+    "  "BP_NAME" [flags] <pattern> [<files>...]\n\n"
     "Flags:\n"
     " -h --help                        print the usage and quit\n"
     " -v --verbose                     print verbose debugging info\n"
@@ -48,10 +48,10 @@ static const char *usage = (
     " -l --list-files                  list filenames only\n"
     " -p --pattern <pat>               provide a pattern (equivalent to bp '\\(<pat>)')\n"
     " -r --replace <replacement>       replace the input pattern with the given replacement\n"
-    " -s --skip <skip pattern>         skip over the given pattern when looking for matches\n"
+    " -s --skip <skip-pattern>         skip over the given pattern when looking for matches\n"
     " -c --context <context>           set number of lines of context to print (all: the whole file, 0: only the match, 1: the line, N: N lines of context)\n"
     " -f --format auto|fancy|plain     set the output format\n"
-    " -g --grammar <grammar file>      use the specified file as a grammar");
+    " -g --grammar <grammar-file>      use the specified file as a grammar");
 
 // Used as a heuristic to check if a file is binary or text:
 #define CHECK_FIRST_N_BYTES 128
diff --git a/grammars/builtins.bp b/grammars/builtins.bp
index 8119573..6c0fc75 100644
--- a/grammars/builtins.bp
+++ b/grammars/builtins.bp
@@ -15,7 +15,8 @@ anglebraces: `< ..%(\n/anglebraces/string) `>
 brackets: `[ ..%(\n/brackets/string) `]
 braces: `{ ..%(\n/braces/string) `}
 parens: `( ..%(\n/parens/string) `)
-string: `" ..%(`\.) `" / `' ..%(`\.) `'
+string: `" ..%string-escape `" / `' ..%string-escape `'
+string-escape: `\ (`x 2 Hex / 1-3 `0-7 / `u 1-4 Hex / .)
 left-id-edge: ^ / <(\x00-x7f!=id-char) / <((\xc0-xdf \x80-xbf)!=id-char)
     / <((\xe0-xef 2\x80-xbf)!=id-char) / <((\xf0-xf7 3\x80-xbf)!=id-char)
 right-id-edge: !id-char
diff --git a/grammars/c++.bp b/grammars/c++.bp
index a48d5a2..1553bb3 100644
--- a/grammars/c++.bp
+++ b/grammars/c++.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: "//" .. $ / "/*" ..%\n "*/"
-string: `" ..%(`\.) `"
+string: `" ..%string-escape `"
 keyword:
     "alignas" / "alignof" / "and" / "and_eq" / "asm" / "atomic_cancel" / "atomic_commit" /
     "atomic_noexcept" / "auto" / "bitand" / "bitor" / "bool" / "break" / "case" / "catch" /
diff --git a/grammars/c.bp b/grammars/c.bp
index 2c74c3d..9940ffe 100644
--- a/grammars/c.bp
+++ b/grammars/c.bp
@@ -7,7 +7,8 @@
 # See the accompanying README.md for more info.
 
 comment: "//" .. $ / "/*" ..%\n "*/"
-string: `" ..%(`\.) `"
+string: `" ..%string-escape `"
+string-escape: `\ (`x 2 Hex / 1-3 `0-7 / .)
 keyword:
     "auto" / "break" / "case" / "char" / "const" / "continue" / "default" / "do" /
     "double" / "else" / "enum" / "extern" / "float" / "for" / "goto" / "if" /
diff --git a/grammars/go.bp b/grammars/go.bp
index c9f7377..71114cf 100644
--- a/grammars/go.bp
+++ b/grammars/go.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: "//" .. $ / "/*" ..%\n "*/"
-string: `" ..%(`\.) `"
+string: `" ..%string-escape `"
 keyword:
     "break" / "default" / "func" / "interface" / "select" / "case" / "defer" / "go" /
     "map" / "struct" / "chan" / "else" / "goto" / "package" / "switch" / "const" /
diff --git a/grammars/javascript.bp b/grammars/javascript.bp
index fdd76a1..76fa586 100644
--- a/grammars/javascript.bp
+++ b/grammars/javascript.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: "//" .. $ / "/*" ..%\n "*/"
-string: `" ..%(`\.) `" / `' ..%(`\.) `' / `/ ..%(`\.) `/
+string: `" ..%string-escape `" / `' ..%string-escape `' / `/ ..%string-escape `/
 keyword:
     "abstract" / "arguments" / "await" / "boolean" / "break" / "byte" / "case" /
     "catch" / "char" / "class" / "const" / "continue" / "debugger" / "default" /
diff --git a/grammars/lisp.bp b/grammars/lisp.bp
index d02a458..b7b89ed 100644
--- a/grammars/lisp.bp
+++ b/grammars/lisp.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: ";" ..$
-string: `" ..%(`\.) `"
+string: `" ..%string-escape `"
 list: parens
 function-def: `(__{defun}__id
 function: function-def ..%parens `)
diff --git a/grammars/lua.bp b/grammars/lua.bp
index 6967f1e..562b44a 100644
--- a/grammars/lua.bp
+++ b/grammars/lua.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: "--" (`[ @eqs=*`= `[ ..%\n (`]eqs`]) / ..$)
-string: `"..%(`\.) `" / `' ..%(`\.) `' / `[ @eqs=*`= `[ ..%\n (`]eqs`])
+string: `"..%string-escape `" / `' ..%string-escape `' / `[ @eqs=*`= `[ ..%\n (`]eqs`])
 table: `{ ..%(table/string/comment/\n) `}
 keyword:
  "and" / "break" / "do" / "else" / "elseif" / "end" / "false" / "for" /
diff --git a/grammars/python.bp b/grammars/python.bp
index 37d6a88..cb5d047 100644
--- a/grammars/python.bp
+++ b/grammars/python.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: `# ..$
-string: "'''" ..%\n "'''" / '"""' ..%\n '"""' / `" ..%(`\.) `" / `' ..%(`\.) `'
+string: "'''" ..%\n "'''" / '"""' ..%\n '"""' / `" ..%string-escape `" / `' ..%string-escape `'
 keyword: "and" / "as" / "assert" / "break" / "class" / "continue" / "def" /
     "del" / "elif" / "else" / "except" / "finally" / "for" / "from" /
     "global" / "if" / "import" / "in" / "is" / "lambda" / "None" / "nonlocal" /
diff --git a/grammars/rust.bp b/grammars/rust.bp
index 97a1e73..108b41a 100644
--- a/grammars/rust.bp
+++ b/grammars/rust.bp
@@ -7,7 +7,7 @@
 # See the accompanying README.md for more info.
 
 comment: "//" .. $ / "/*" ..%(comment / \n) "*/"
-string: `" ..%(`\.) `"
+string: `" ..%string-escape `"
 keyword:
     "as" / "break" / "const" / "continue" / "crate" / "else" / "enum" / "extern" /
     "false" / "fn" / "for" / "if" / "impl" / "in" / "let" / "loop" / "match" /
diff --git a/grammars/shell.bp b/grammars/shell.bp
index ff13d0b..72b83cc 100644
--- a/grammars/shell.bp
+++ b/grammars/shell.bp
@@ -7,8 +7,9 @@
 # See the accompanying README.md for more info.
 
 comment: `#..$
-string: `" ..%(`\./subcommand/\n) `" / `' ..%\n `' / "<<" _ @delim=id _$ ..%\n (^delim$)
-subcommand: `` ..%\n `` / "$" parens
+string: `" ..%(string-escape / subcommand / \n) `" / `' ..%\n `' / "<<" _ @delim=id _$ ..%\n (^delim$)
+string-escape: `\ `",`
+subcommand: `` ..%\n `` / "$" (parens/braces)
 keyword:
     "echo" / "read" / "set" / "unset" / "readonly" / "shift" / "export" / "if" / "fi" /
     "else" / "while" / "do" / "done" / "for" / "until" / "case" / "esac" / "break" /